nemo_gym.web.composed_backend

Backend-neutral composition of a web browser driver and task evaluator.

Module Contents

Classes

Name	Description
`ComposedWebBackend`	Implement the common environment protocol from independent roles.
`WebBrowserDriver`	Own the live browser only; model prompting and scoring live elsewhere.
`WebTaskEvaluator`	Score a completed task without owning the browser lifecycle.

API

class nemo_gym.web.composed_backend.ComposedWebBackend(
    driver: nemo_gym.web.composed_backend.WebBrowserDriver,
    evaluator: nemo_gym.web.composed_backend.WebTaskEvaluator
)

Implement the common environment protocol from independent roles.

The driver owns Chromium/Playwright/PyAutoGUI mechanics. The evaluator owns benchmark scoring. The agent remains an HTTP client of this backend and never imports either implementation.

_observation

WebObservation | None = None

_task

WebTask | None = None

nemo_gym.web.composed_backend.ComposedWebBackend._require_active() -> tuple[nemo_gym.web.models.WebTask, nemo_gym.web.models.WebObservation]

nemo_gym.web.composed_backend.ComposedWebBackend.close() -> None

nemo_gym.web.composed_backend.ComposedWebBackend.evaluate(
    final_answer: str | None = None
) -> nemo_gym.web.models.WebVerifierResult

nemo_gym.web.composed_backend.ComposedWebBackend.observe() -> nemo_gym.web.models.WebObservation

nemo_gym.web.composed_backend.ComposedWebBackend.reset(
    task: nemo_gym.web.models.WebTask
) -> tuple[nemo_gym.web.models.WebObservation, dict[str, typing.Any]]

nemo_gym.web.composed_backend.ComposedWebBackend.step(
    action: nemo_gym.web.models.WebAction
) -> nemo_gym.web.models.WebStepResult

class nemo_gym.web.composed_backend.WebBrowserDriver()

Protocol

Own the live browser only; model prompting and scoring live elsewhere.

nemo_gym.web.composed_backend.WebBrowserDriver.close() -> None

nemo_gym.web.composed_backend.WebBrowserDriver.evaluation_context() -> typing.Any

Return process-local state required by a colocated evaluator.

nemo_gym.web.composed_backend.WebBrowserDriver.observe() -> nemo_gym.web.models.WebObservation

nemo_gym.web.composed_backend.WebBrowserDriver.reset(
    task: nemo_gym.web.models.WebTask
) -> tuple[nemo_gym.web.models.WebObservation, dict[str, typing.Any]]

nemo_gym.web.composed_backend.WebBrowserDriver.step(
    action: nemo_gym.web.models.WebAction
) -> nemo_gym.web.models.WebStepResult

class nemo_gym.web.composed_backend.WebTaskEvaluator()

Protocol

Score a completed task without owning the browser lifecycle.

nemo_gym.web.composed_backend.WebTaskEvaluator.close() -> None

nemo_gym.web.composed_backend.WebTaskEvaluator.evaluate(
    task: nemo_gym.web.models.WebTask,
    observation: nemo_gym.web.models.WebObservation,
    final_answer: str | None,
    browser_context: typing.Any
) -> nemo_gym.web.models.WebVerifierResult

nemo_gym.web.composed_backend.WebTaskEvaluator.prepare(
    task: nemo_gym.web.models.WebTask,
    observation: nemo_gym.web.models.WebObservation,
    browser_context: typing.Any
) -> None

Capture evaluator state required before the policy starts acting.